"OpenAI Gym" matching MCP servers:

A tiny MCP server that wraps Perseus Vault to provide persistent, encrypted, local-first memory for OpenAI Codex agents, enabling them to remember project conventions, decisions, and context across sessions.

An MCP server that provides long-term memory and semantic search using Qdrant and OpenAI embeddings, with tools for storing, searching, and managing knowledge.

Enables semantic search, code exemplar lookup, knowledge-graph statistics, and cached retrieval over locally ingested notebook and Markdown content through MCP.

Intelligent knowledge base system that enables users to process documents in 25+ formats, perform semantic search and Q\&A through vector retrieval. Supports multiple AI models including OpenAI and DouBao with local processing capabilities.

A research assistant server that enables saving, organizing, and retrieving research content with semantic search using ChromaDB and OpenAI embeddings.

Lets Claude read and manage Speediance Gym Monster training data — session history, per-set logs, exercise progress, rowing and heart-rate stats, custom workouts and schedule — plus a coaching memory of goals, injuries and preferences. It runs self-hosted on the user's own machine, talking directly to the user's account and keeping stored data local.

Transforms YouTube into a queryable knowledge source with search, video details, transcript analysis, and AI-powered tools for summaries, learning paths, and knowledge graphs. Features quota-aware API access with caching and optional OpenAI/Anthropic integration for advanced content analysis.

A shared memory layer for AI agents — one memory.md synced across Claude Desktop, Cursor, Claude Code, OpenAI Codex, and any MCP client.

Enables AI assistants to save and search bookmarks with semantic search using OpenAI, allowing storage of URLs with metadata and intelligent retrieval across collections.

Enables lossless context management for OpenAI Codex CLI by capturing and compressing conversation history in SQLite, with lexical recall via MCP tools.

OpenKai is an open-source MCP server that gives AI agents persistent memory across conversations, supporting core, long-term, short-term, episodic, and working memory types with goals, emotional intelligence, and temporal queries.

Enables chat with multiple LLM providers (OpenAI and Anthropic) while maintaining persistent conversation memory. Provides extensible tool framework for various operations including echo functionality and conversation storage/retrieval.

Enables AI assistants to save, retrieve, and manage research content using ChromaDB vector storage with semantic search, topic organization, and automatic deduplication powered by OpenAI embeddings.

Open-source AI memory layer for LLM agents. Importance scoring, temporal decay, hierarchical memory (facts, summaries, themes), YMYL prioritization, and active retrieval with contradiction detection. Supports OpenAI, Anthropic, Ollama. Local-first with SQLite + FAISS.

A Model Context Protocol server that enables intelligent document search and retrieval from PDF collections, providing semantic search capabilities powered by OpenAI embeddings and ChromaDB vector storage.

Enables voice captures from a smart ring to search and append notes in a local Obsidian vault and query an OpenAI-compatible AI agent, returning answers as phone notifications.

Enables real-time communication and shared vector memory between Claude Code, OpenAI Codex CLI, and Google Gemini CLI. It allows different AI platforms to exchange messages, share context, and collaborate through a unified MCP interface.

MCP server that integrates OpenAI Codex with Open Knowledge Format (OKF), enabling knowledge bundle validation, capture, diffing, and workflow automation through natural language.

A local knowledge base server that connects to AI assistants, turning markdown files into a semantically searchable memory layer via OpenAI embeddings and SQLite.

Enables searching local OpenAI Codex conversation history by keywords, project, date, or role, listing sessions, and retrieving exact supporting messages through MCP tools.

A fully local AI stack that provides OpenAI/Anthropic-compatible LLM API, embeddings, mem0 memory, and second-brain RAG via MCP tools, all running independently with no cloud dependencies.

Facilitates knowledge graph representation with semantic search using Qdrant, supporting OpenAI embeddings for semantic similarity and robust HTTPS integration with file-based graph persistence.

A local Mem0 MCP server for macOS with a menu bar toggle, storing memories locally in Chroma and using any OpenAI-compatible LLM for fact extraction.

Enables semantic memory storage and retrieval with natural language queries, deployed on Vercel with PostgreSQL pgvector and OpenAI embeddings.

SQLite-backed memory storage for MCP agents with optional semantic search via OpenAI embeddings, enabling agents to remember, recall, and manage contextual information across sessions.

MCP server that indexes your Obsidian notes into a Milvus vector database and enables querying them via a local or OpenAI LLM, with real-time synchronization.

Enables coding agents to write and recall long-term memories through a local, MCP-ready pipeline that extracts six memory categories on write and dispatches them by category view on read. Supports external OpenAI-compatible LLM endpoints and local Neo4j/Qdrant/Redis storage.

Enables MCP-compatible agents to automatically distill conversations into durable local memory and recall relevant context on demand through seven MCP tools, using user-configurable OpenAI-compatible endpoints for extraction and embeddings.

Stores and retrieves project context using OpenAI vector stores, enabling AI editors to remember and recall project knowledge across sessions.

Enables reflective thinking and memory storage with support for multiple AI providers (OpenAI, Anthropic, Gemini, Ollama) or local fallback. Stores contextual memories locally and provides tools for reflection, questioning, note-taking, and summarization across different conversation keys.